Library · Optimization & control
What Constrained Optimization got wrong, from 63 theses
Summary written by a model from the records below: The records evaluate various constrained optimization methods across power systems, robotics, control, portfolio management, and trajectory planning. Many approaches fail due to solver infeasibility, over-conservative constraint definitions, complete omission of physical constraints, or the computational burden of non-convex projection and evaluation. These records come from graduate theses, 2021 to 2026, each labeled with its degree where the repository states it, and each links to its thesis. They were extracted by language models reading the full text, so treat each as a lead to read, not a verdict.
Plus 10 problems the authors left open, listed at the end.
Failure modes, by theses reporting them
Select a mode to jump to its records.
Omitting or weakly enforcing constraints causes physical limit violations and system instability
Unconstrained formulations, unconstrained state optimization, and expectation-based average constraints permit severe physical violations and dynamic instability in power, robotics, and tracking systems. Omitting necessary contact or dynamic constraints leads to nonphysical distortions, solution degeneracy, and inferior performance compared to properly constrained approaches.
Tried and failed
semidefinite relaxation optimal power flow applied to networked DC microgrids control. Outcome: unstable. Reason: steady-state operating points lacked negative eigenvalues without explicit dynamic stability constraints
Networked DC microgrids control system for optimal power exchange with guaranteed stability · Imperial · PhD
Tried and failed
expectation-based constraint formulations in constrained optimization applied to stochastic optimal power flow. Reason: optimizing average constraints permitted high-frequency individual limit violations across scenarios
Machine Learning and Quantum Computing for Optimization Problems in Power Systems · Virginia Tech · Doctorate
Tried and failed
unconstrained reinforcement learning for constrained control applied to power distribution network optimization. Reason: optimizing reward without constraint enforcement causes severe physical capacity and thermal line limit violations
Multi-agent optimization and learning methods for sustainable, smart and resilient power distribution systems and microgrids · Iowa State · PhD
Lost to a baseline
On the IEEE 14-bus benchmark, reinforcement learning (RL) achieved a lower optimality gap deviation from MIPS (0.6%) than the proposed ICNN (1.53 ± 0.27%), albeit violating feasibility constraints.
Data-driven Methods for Optimal Power Flow in Smart Grids · York University · PhD
Lost to a baseline
Proposed MPC controller achieved higher cost (2.0545x10^4) than unconstrained optimal LQG (893.5569), though LQG violated the constraint (3.9272 > 2).
Robust and stochastic receding horizon control · Oxford · PhD
Considered and rejected
Considered and rejected: Rejected unconstrained adversarial optimization with linear search over schedules in favor of Lagrangian relaxation / differential method of multipliers with a derived epsilon constraint.
Improving the Robustness of Natural Language Processing to Dialects and Language Variation · Georgia Tech · PhD
Considered and rejected
Considered and rejected: Rejected simple clipping of transformed control variables under actuator saturation because it compromises feedback linearization decoupling, opting instead for constrained quadratic optimization with weighting.
Control of multi-temperature transport systems · TU Wien · PhD
Tried and failed
unconstrained parameter regression without symmetry constraints applied to lattice parameter prediction from diffraction patterns. Outcome: overfit. Reason: optimizing unconstrained parameters achieved lower training loss through nonphysical distortions, degrading generalization performance
Enabling Autonomous high-throughput XRD-based Phase Discovery in Thin film systems · Cornell · PhD
Considered and rejected
Considered and rejected: Rejected unconstrained polynomial waypoint perturbation functions due to poor linear least-squares curve fits and training instabilities during RL optimization.
Perception-aware planning for differentially flat robots · MIT · PhD
Considered and rejected
Considered and rejected: Rejected training an unconstrained deep FBSDE policy and augmenting a control barrier function safety filter at test-time, because it leads to sub-optimal policies compared to training in a constrained state-space.
Scalable and Safe Deep Learning Architectures for Stochastic Optimal Control Using Forward-Backward Stochastic Differential Equations · Georgia Tech · PhD
Tried and failed
kinematic trajectory estimation without dynamic constraints applied to satellite orbit and gravity field determination. Reason: nominal and true trajectories could not be reconciled without joint dynamical parameter estimation
Theory and application of extremely precise frequency standards on low Earth orbit to the determination of geopotential time-variability · UT Austin · PhD
Tried and failed
unconstrained parameter optimization with high-eccentricity search spaces applied to satellite constellation geometry optimization. Outcome: worse than baseline. Reason: increased orbital degrees of freedom and extreme eccentricity did not improve information matrix optimality over structured baselines
Leveraging optical clocks and relativistic geodesy for multi-satellite missions and deep space navigation · Georgia Tech · PhD
Tried and failed
nonlinear model predictive control without steady-state references applied to over-actuated trajectory tracking. Outcome: unstable. Reason: unconstrained state optimization caused solver convergence issues and severe control oscillations
Path tracking control of a multi-actuated autonomous vehicle at the limits of handling. · Cranfield · PhD
Tried and failed
kinematic-inertial estimation without contact constraints applied to legged robot state estimation. Outcome: unstable. Reason: omitting contact measurements leaves unconstrained degrees of freedom leading to solution degeneracy
Proprioceptive State Estimation for Legged Robots with Probabilistic and Hybrid Kinodynamics · Georgia Tech · PhD
Lost to a baseline
Differential inverse kinematics achieved lower RMSE (0.0036m x, 0.0044m y, 0.00055m z) than gradient projection (0.0037m, 0.0034m, 0.0070m) and ANFIS (0.1309m, 0.0209m, 0.1261m), but failed joint limit constraints.
Development of Methodologies, Mechatronic Solutions and Controls for Upper Body Rehabilitative Robotics · Politecnico di Torino · PhD
Overly conservative or rigid constraint formulations degrade performance and trap optimizers
Applying strict parameter bounds, diagonally dominant approximations, or heavily weighted constraints often leads to over-regularization and traps optimizers in suboptimal local minima. These overly conservative restrictions increase travel times, weaken objective bounds, and cause worse empirical performance than flexible or unconstrained alternatives.
Tried and failed
two-stage stochastic optimization with fairness constraints applied to power grid resilience investment. Reason: Strict efficiency constraints cause non-monotonic worst-case risk reduction as investment budget increases
Decision-making under uncertainty in power systems and economics · UT Austin · PhD
Tried and failed
diagonally dominant approximations for positive semidefiniteness applied to convex relaxations of polynomial optimization. Outcome: worse than baseline. Reason: diagonal dominance is overly conservative compared to exact semidefinite constraints, yielding substantially weaker bounds
Advances in Nonconvex and Robust Optimization · MIT · PhD
Tried and failed
heavily weighted constraints in method of moving asymptotes applied to density-based topology optimization. Outcome: worse than baseline. Reason: overly strict constraint weights caused optimizer to get trapped in suboptimal local minima with poor performance
High-Efficiency Topology Optimization for Very Large-Scale Integrated-Photonics Inverse Design · Georgia Tech · PhD
Tried and failed
non-negative weight constraints applied to confounder balancing weights estimation. Outcome: worse than baseline. Reason: constraining weights to the simplex hurt empirical performance compared to unconstrained optimization
Adversarial Machine Learning Methods for Causal Inference under Unmeasured Confounding · Cornell · PhD
Tried and failed
optimization-based block preconditioner tuning applied to stiff PDE system linear solvers. Outcome: worse than baseline. Reason: optimization over the affine subspace was overly constrained
New models and numerical methods for partial differential equations applied to spatial stoichiometric aquatic ecosystems · Texas Tech · PhD
Tried and failed
raw constraint sensitivity regularization without relevance filtering applied to chance-constrained trajectory optimization. Reason: over-constrains the problem and fails to generate conservative collision-avoidance trajectories
Games of Pursuit-Evasion with Multiple Agents and Subject to Uncertainties · Georgia Tech · PhD
Tried and failed
uniform risk allocation across constraints applied to chance-constrained trajectory optimization. Outcome: worse than baseline. Reason: leads to overly conservative trajectories and suboptimal final covariance ellipsoid volumes compared to optimized allocation
Model-Based and Data-Driven Covariance Control: Theory and Applications · Georgia Tech · PhD
Tried and failed
constrained optimal control with strict multi-derivative bounds applied to vehicle speed trajectory planning. Outcome: worse than baseline. Reason: strict acceleration and jerk bounds prevented overshooting, increasing total travel time compared to unconstrained trajectory
An Interdisciplinary and Probabilistic Treatment of Contemporary Highway Design Standards · Virginia Tech · Doctorate
Tried and failed
naive constraint conditions in constrained optimization applied to regularized neural network training. Outcome: worse than baseline. Reason: naive constraints caused over-regularization that harmed training performance
METHODOLOGICAL ADVANCES IN REAL-WORLD COMPUTER VISION: ROBUSTNESS, EFFICIENCY AND HUMAN PREFERENCE ALIGNMENT · Cornell · PhD
Lost to a baseline
Linear RTMPC and its learned policy achieved larger nominal tracking error than standard MPC when position constraints were tight, due to conservative tube-based constraint tightening.
Efficient Imitation Learning for Robust, Adaptive, Vision-based Agile Flight Under Uncertainty · MIT · PhD
Lost to a baseline
Bernstein/RBF positive semi-definite parameterizations exhibit slight accuracy degradation compared to Chebyshev polynomials due to increased conservativeness of stability constraints.
High-dimensional data driven parameterized macromodeling · Politecnico di Torino · PhD
Considered and rejected
Considered and rejected: Rejected continuous/simultaneous optimization of robot motion and physical parameters in an alternating sequence (optimizing motion, then body parameters, then actuators successively) because parameter constraints lock the robot into suboptimal designs or infeasible states.
Co-Optimization and Co-Learning Methods for Automated Design of Rigid and Soft Robots · MIT · PhD
Considered and rejected
Considered and rejected: Rejected convexification of unsafe obstacle regions for constrained trajectory optimization due to overly restrictive geometric assumptions.
Decision-Making Architectures for Control of Uncertain Systems · Georgia Tech · PhD
Considered and rejected
Considered and rejected: Rejected optimal control with artificial potentials for counter-swarming due to high constraints and prescribed trajectories that degrade swarm flexibility.
DEEP LEARNING METHODS FOR DECENTRALIZED DECISION-MAKING IN COUNTERSWARM ENGAGEMENTS · Naval Postgraduate School · Master's
Strict, conflicting, or non-smooth constraints cause mathematical infeasibility and solver non-convergence
Solvers encounter divergence, primal infeasibility, and numerical breakdown when strict obstacle, geometric, or dynamic boundary constraints cannot be satisfied simultaneously. Direct constraint tightening, lack of dynamic feasibility warm-starts, and unbounded non-smooth terms prevent algorithms from locating feasible trajectories and operating states.
Tried and failed
equality-constrained nonsmooth Newton optimization applied to industrial cogeneration power targeting. Outcome: did not converge. Reason: equality formulation failed to converge across initial guesses, requiring inequality constraints
Nonsmooth Methods for Process Integration · MIT · PhD
Tried and failed
gradient-based optimization with numerical simulation constraints applied to thermodynamic cycle design optimization. Outcome: did not converge. Reason: numerical solver tolerances and cycle constraints disrupted gradient calculation and convergence
A Method for the Conceptual Design of Integrated Variable Cycle Engines and Aircraft Thermal Management Systems · Georgia Tech · PhD
Tried and failed
restricted affine policy for chance-constrained optimization applied to stochastic power system dispatch. Outcome: did not converge. Reason: Restricted policy parameterization lacked expressiveness to satisfy chance constraints under high uncertainty variance.
Machine Learning and Quantum Computing for Optimization Problems in Power Systems · Virginia Tech · Doctorate
Tried and failed
mixed-integer nonlinear programming applied to transient stability optimization in power converters. Outcome: did not converge. Reason: numerical instability and division by zero caused by unbounded trigonometric tangent terms in constraints
Modeling and enhancing transient stability of grid-forming converters · Imperial · PhD
Tried and failed
sequential path stepping gradient descent optimization applied to constrained robotic trajectory planning. Outcome: did not converge. Reason: algorithm failed in environments with tight obstacles and long paths
Remote robotic manipulation task execution using affordance primitives · UT Austin · PhD
Tried and failed
tightening constraints directly in model predictive control applied to nonlinear trajectory tracking under uncertainty. Outcome: did not converge. Reason: direct constraint tightening caused severe optimization infeasibility compared to predictive reference generation
Learning-based Model Predictive Control for Aerial Vehicles · Penn · PhD
Tried and failed
sampling-based trajectory optimization with multimodal proposals applied to cluttered motion planning. Outcome: did not converge. Reason: failed to find feasible trajectories despite increasing sample counts and proposal covariances in constrained environments
Robot Learning using Tensor Networks · EPFL · PhD
Tried and failed
dynamic movement primitives under waypoint constraints applied to robot trajectory generation with obstacle avoidance. Outcome: did not converge. Reason: hyperparameters failed to reliably find trajectories satisfying both intermediate via-point and obstacle avoidance constraints
Automatically Encoding, Modifying, and Finding Robot Skills to Repair High-Level Tasks · Cornell · PhD
Tried and failed
sequential quadratic programming without dynamic feasibility warm-start applied to constrained trajectory optimization. Outcome: did not converge. Reason: omitting initial dynamic feasibility checks caused consistent primal infeasibility during nonlinear optimization
Dynamic whole-body planning for humanoids in confined spaces : a morphology-aware synthesis approach · UT Austin · PhD
Tried and failed
single-variable boundary projection under stoichiometric constraints applied to chemical process efficiency target optimization. Reason: adjusting only one feed flow violated the minimum stoichiometric lower-bound constraints, causing mathematical infeasibility
Promoting sustainability in chemical process design using process modelling, environmental assessment and decision making · Imperial · PhD
Tried and failed
quadratic programming with strict physiological bound constraints applied to musculoskeletal inverse dynamics torque estimation. Outcome: did not converge. Reason: kinematic irregularities and non-smooth dynamics made strictly bounded constraints mathematically infeasible
Understanding motor control and impairment: An upper-limb model for muscular assessment · EPFL · PhD
Considered and rejected
Considered and rejected: Rejected hard obstacle constraints in Koopman MPC because model prediction inaccuracies cause infeasibility and deadlock near the constraint boundary.
Koopman Dynamic Modeling and Control for Robotic Systems Making and Breaking Contact · MIT · PhD
Black-box and heuristic search algorithms fail to navigate complex constraint spaces
Nelder-Mead, Bayesian optimization, genetic algorithms, and greedy heuristics struggle to find feasible solutions or become trapped in local optima under complex constraints. Decoupled heuristics and extreme objective weightings frequently violate target constraints, yielding zero objective value or falling behind simpler search baselines.
Tried and failed
Nelder-Mead simplex optimization applied to constrained power dispatch optimization. Outcome: did not converge. Reason: Objective space discontinuities caused by high-persistence constraints trapped the solver in local minima
Economic, System, and Community-Based Optimization of Off-Grid Wave Energy Conversion · University of Washington · PhD
Tried and failed
Single-objective extreme weighting in multi-objective heuristic search applied to constrained spatial path finding. Outcome: worse than baseline. Reason: Extremes degrade search efficiency and Pareto trade-offs compared to balanced joint optimization.
Semantically diverse and spatially constrained queries · Iowa State · PhD
Tried and failed
multi-objective evolutionary optimization for single target priority applied to constrained resource allocation. Outcome: worse than baseline. Reason: Pareto compromise solutions underperform dedicated single-objective optimization when only one metric is prioritized
Integrating social equity into sustainable programming of road projects : a quantitative approach · UT Austin · PhD
Tried and failed
decoupled objective heuristics for constrained diffusion applied to influence maximization with competing constraints. Reason: heuristics either over-activated non-targets yielding zero value or activated too few targets
Constrained submodular optimization and applications in information diffusion · Iowa State · PhD
Lost to a baseline
Trust-region algorithm and genetic algorithm for constrained optimization were matched or outperformed by a simpler two-stage coarse grid search
Modeling Healthcare Policy: From Calibration to Optimization · University of Washington · PhD
Tried and failed
distance-thresholded active learning exploration applied to chemical reaction optimization. Outcome: worse than baseline. Reason: Similarity constraints failed to outperform random sampling in small sample-size regimes
Tried and failed
Standard Bayesian optimization and genetic algorithms applied to Constrained black-box optimization. Reason: Struggled to find feasible points or violated constraints without explicit mixed-integer programming integration.
Sequential black-box optimization via global optimization of tree ensembles · Imperial · PhD
Tried and failed
Gaussian process Bayesian optimization with weighted expected improvement applied to multi-objective circuit parameter optimization. Outcome: did not converge. Reason: trapped in local optima and failed to satisfy multiple stringent constrained specifications simultaneously
Efficient optimization methods for analog/mixed-signal integrated circuits via machine learning · UT Austin · PhD
Considered and rejected
Considered and rejected: Rejected single-objective Bayesian optimization with rigid user constraints or fused metrics because it fails to capture high-dimensional resource trade-offs and substitutability.
Design and Management Strategies for Hardware Accelerators · Duke · PhD
Surrogate objectives and heuristic constraint relaxations underperform standard baselines
Relying on unconstrained surrogate loss functions, decoupled line searches, or unrolled projected gradient descent fails to properly align gradients with feasibility requirements. These relaxed heuristics and policy optimization methods underperform standard baselines such as regular gradient descent, proximal policy optimization, and simple projection.
Tried and failed
unconstrained neural network surrogate loss learning applied to decision-focused portfolio optimization. Outcome: worse than baseline. Reason: unconstrained non-convex surrogate loss functions lead to poor optimization and worse decision quality than standard two-stage baselines
Decision-Focused Learning for the Masses With Applications to Public Health · Harvard · PhD
Tried and failed
relying solely on line search for constraint feasibility applied to constrained reinforcement learning policy optimization. Outcome: worse than baseline. Reason: omitting gradient-level constraint alignment provided insufficient correction compared to combining gradient optimization with line search
Risk-Aware Reinforcement Learning with Safety Constraints · MIT · PhD
Tried and failed
unrolled projected gradient descent with surrogate objective applied to approximating constrained convex optimization. Outcome: worse than baseline. Reason: traditional gradient descent achieves better convergence accuracy at higher iteration counts
Aligning Machine Learning and Robust Decision-Making · MIT · PhD
Tried and failed
regret-based Bayesian optimization acquisition function applied to privacy-constrained personalization querying. Outcome: worse than baseline. Reason: Failed to outperform uniform querying across privacy-constrained personalization simulations.
Essays on the Decision Value of Data in Marketing Measurement and Targeting · Penn · PhD
Lost to a baseline
Under the distortion constraint (d_hat = 0.2), Constrained Thompson Sampling was beaten in long-term average cost by Unconstrained Thompson Sampling in the coexistence scenario, and Constrained EXP3 was beaten in average cost by Unconstrained EXP3.
On the Value of Online Learning for Cognitive Radar Waveform Selection · Virginia Tech · Doctorate
Lost to a baseline
Constrained minimum-variance portfolio using RSVAR (0.087) had a statistically significantly lower Sharpe ratio than the naive rule (0.112) on Dataset 1.
Essays on Financial Economics · Penn · PhD
Considered and rejected
Considered and rejected: Rejected TRPO-based Constrained Policy Optimization (CPO) because PPO consistently outperformed TRPO on sample efficiency
Light Water Reactor Loading Pattern Optimization with Reinforcement Learning Algorithms · MIT · PhD
Considered and rejected
Considered and rejected: Rejected KKT-constrained gradient descent in favor of standard GD with projection/bounding onto [0,1] when the mixing matrix is overdetermined with independent columns
Linear Spectral Unmixing Algorithms for Abundance Fraction Estimation in Spectroscopy · York University · Master's
Considered and rejected
Considered and rejected: Rejected standard convex weighted estimator beta * theta_SL + (1 - beta) * theta_L with optimal weights learned via constrained least squares, because optimal prediction error does not guarantee smaller parameter estimation error.
Optimal and Safe Semi-supervised Estimation and Inference for High-dimensional Linear Regression · Cornell · PhD
Exact constraint evaluation and non-convex projections impose prohibitive computational burdens
Real-time execution and nonlinear optimization struggle with the high computational cost of evaluating projections over general non-convex sets and handling explicit flight-time constraints. Semidefinite matrix inequality constraints and greedy constraint evaluations introduce excessive runtimes that render them impractical compared to simpler functional representations.
Considered and rejected
Considered and rejected: Rejected 2-clothoid segment constrained optimization using fmincon because iterative numerical solvers cannot guarantee convergence in real-time execution
Autonomous Vehicle Waypoint Navigation Using Hyper-Clothoids · Virginia Tech · Doctorate
Considered and rejected
Considered and rejected: Position-level projected gradient descent for constrained OT was rejected because evaluating projections over general non-convex feasible sets is computationally intractable.
Routing Optimization for Transport and Sustainability · Tübingen · PhD
Lost to a baseline
Sensitivity-Driven Greedy Algorithm (3.95) satisfied OAR dose-volume constraints in the initial approximate solve where unweighted (P2) did not, but required ~2000s vs 2.8s
Optimization Formulations and Algorithms for Cancer Therapy · University of Washington · PhD
Considered and rejected
Considered and rejected: Rejected using explicit nonlinear flight-time constraints in NLP optimizers (e.g. SNOPT/IPOPT) due to unnecessary numerical optimization burden compared to explicit PST flight-time functions.
Spacecraft trajectory optimization using many embedded Lambert problems · UT Austin · PhD
Considered and rejected
Considered and rejected: Rejected Schur stability and Lyapunov matrix inequality (SDP) constraints for Koopman learning due to nonconvexity and computational intractability on large systems.
From robotics to healthcare: toward clinically-relevant 3-D human pose tracking for lower limb mobility assessments · Boston University · PhD
Left open by the authors
Problems the authors named and did not get to.
Left open
Optimize dynamic graph linkage addition and removal strategies for transactive energy peer-to-peer microgrid simulations with power flow constraints. Blocker: Lack of specified mathematical objective function and baseline simulation codebase
A Mycorrhizal Model for Transactive Energy Markets · Virginia Tech · Doctorate
Left open
Develop an optimization framework to synchronize multi-energy systems including hydrogen, gas, heating, and cooling networks with electrical grid flexibility needs. Blocker: Lacks specific mathematical formulations, constraints, network topologies, and performance benchmarks for the integrated multi-energy system
Improving the Flexibility of Future Power Systems : Provision of Flexibility Services to the System Operators by Different Energy Resources · University of Vaasa · PhD
Left open
Develop a CoED graph neural network pipeline to predict AC-OPF solutions that strictly satisfy power grid physical constraints. Blocker: None
Developing Differentiable Toolkits for Computational Biology · Harvard · PhD
Left open
Develop power flow algorithms integrated with electricity market frameworks accounting for market prices, generation costs, and system constraints. Blocker: The unfinished work describes an extremely broad research direction (optimal power flow / market clearing) without a concrete formulation, objective, or target algorithm.
Power Flow Calculation of Power Systems with Renewable Penetration and AC/DC grids · University College Dublin · PhD
Left open
Optimize resource overhead for photonic graph state generation protocols under varying physical and circuit constraints. Blocker: Lacks specific target metrics, objective functions, or concrete constraint formulations
Controlling Quantum Systems for Computation and Communication · Virginia Tech · Doctorate
Left open
Theoretically analyze why 2-OPT-C yields significant query efficiency improvements over competing constrained Bayesian optimization methods. Blocker: None
PRACTICAL AND THEORETICAL ADVANCES IN CONSTRAINED BAYESIAN OPTIMIZATION AND BAYESIAN OPTIMIZATION FOR MACHINE LEARNING SYSTEMS · Cornell · PhD
Left open
Impose value function constraints on offline diverse skill extraction and evaluate discriminator-free successor feature objectives for near-optimal performance. Blocker: None
Structured, Constrained and Creative Learning · Tübingen · PhD
Left open
Benchmark the ML-based decomposition heuristic on highly-constrained electric vehicle routing problem benchmark instances with extra operational constraints. Blocker: None
Leveraging Machine Learning Methods to Solve Electric Vehicle Routing Problem Variants · University College Dublin · PhD
Left open
Derive performance bounds comparing receding-horizon regret-optimal control to infinite-horizon constrained regret-optimal policy using MPC proof techniques. Blocker: None
Optimal Control under Uncertainty: From Regret Minimization to Distributional Robustness · EPFL · PhD
Left open
Formulate and implement robust Omega ratio portfolio optimization models with explicit factor exposure constraints. Blocker: None
Essays on portfolio optimization and estimation risk · University College Dublin · PhD
Who has worked on this
Authors of the public theses cited on this page, most-cited first.
- Sarthak Gupta · Virginia Tech · Doctorate · 2023
Machine Learning and Quantum Computing for Optimization Problems in Power Systems - William Barr Held · Georgia Tech · PhD · 2026
Improving the Robustness of Natural Language Processing to Dialects and Language Variation - Anna Shchetkina · Penn · PhD · 2026
Essays on the Decision Value of Data in Marketing Measurement and Targeting - Varun Agrawal · Georgia Tech · PhD · 2025
Proprioceptive State Estimation for Legged Robots with Probabilistic and Hybrid Kinodynamics - Yixuan Jiang · Cornell · PhD · 2025
METHODOLOGICAL ADVANCES IN REAL-WORLD COMPUTER VISION: ROBUSTNESS, EFFICIENCY AND HUMAN PREFERENCE ALIGNMENT - Theodoros Koukouvinos · MIT · PhD · 2025
Advances in Nonconvex and Robust Optimization - Cormac O'Neill · MIT · PhD · 2025
Koopman Dynamic Modeling and Control for Robotic Systems Making and Breaking Contact - Ming-Chiang Chang · Cornell · PhD · 2025
Enabling Autonomous high-throughput XRD-based Phase Discovery in Thin film systems - Seong Ho Pahng · Harvard · PhD · 2025
Developing Differentiable Toolkits for Computational Biology - Sanket Shah · Harvard · PhD · 2025
Decision-Focused Learning for the Masses With Applications to Public Health - Meng Feng · MIT · PhD · 2025
Risk-Aware Reinforcement Learning with Safety Constraints - Rares C. Cristian · MIT · PhD · 2025
Aligning Machine Learning and Robust Decision-Making
Checking a claim in this area?
We can run the same search on any method or claim. If nothing turns up, we will say so, and that proves nothing on its own.